© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75324
    Prev
    Next
    INDEX
    Explanations

    poultry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jump
    0.30
    教材
    0.30
    껴
    0.28
     remediation
    0.27
    replacement
    0.27
     Bloomington
    0.26
     curriculum
    0.26
     Linden
    0.26
    riculum
    0.26
    Forge
    0.26
    POSITIVE LOGITS
     ഒറ്റ
    0.30
    psych
    0.29
     '/',
    0.27
     النفس
    0.27
     $\%$
    0.27
    وشن
    0.27
     Millionen
    0.27
     SHF
    0.27
     stroke
    0.27
     menyelesaikan
    0.27
    Activations Density 0.001%

    No Known Activations